Coding agentSoftware development
Agentless
Solve software defects through structured localization, repair, and patch validation.
- Stars
- 2,080
- Forks
- 235
- Updated
- Updated Jul 9, 2026
MIT
Solve software defects through structured localization, repair, and patch validation.
Agentless replaces a continuously interactive agent with a three-stage process: fault localization, candidate repair, and patch validation. It narrows an issue from files to classes or functions and then exact edit locations, samples several diff patches, and reranks them using regression and reproduction tests. The project mainly targets SWE-bench-style repair experiments and requires a Python 3.11 environment plus an OpenAI API key.
Resource types
Use cases
Runtime
Capabilities
Runs an open-source coding agent in your terminal with build and read-only planning modes.
Run the Codex coding agent locally from your terminal.
Public GitHub facts last synced Jul 10, 2026.
Edit code, run commands, and use tools with an agent in your IDE or terminal.
Use lower-cost models for coding, commands, and interface testing in the terminal.